Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· Developer Tools
Cortex Memory
Long-term structured memory with knowledge graph, entity tracking, temporal reasoning, and cross-session recall. Powered by the Cortex API.
skill openclawclawhub Free
Long-term structured memory with knowledge graph, entity tracking, temporal reasoning, and cross-session recall. Powered by the Cortex API.
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.2
Provenance
- Publisher
- matthewubundi
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Cortex Memory
Cortex gives you a structured long-term memory that goes beyond what memory_search can do. It extracts facts, entities, and relationships from text, stores them in a knowledge graph, and retrieves them using hybrid search (BM25 + semantic + temporal + graph traversal). Use Cortex when you need to: Recall information across past sessions Understand how concepts, people, or projects relate to each other Track what changed over time (superseded facts, belief drift) Find things that memory_search returns noisy or incomplete results for Do NOT use Cortex for simple lookups that memory_search handles well (recent session context, keyword matches in today's log). Use native memory first; escalate to Cortex for deeper queries. If @cortex/openclaw-plugin is also installed: The plugin automatically injects Cortex memories before every turn inside a <cortex_memories> tag. If you see <cortex_memories> in the current context, Cortex has already been queried for this turn β do NOT call recall again unless you need a different query (e.g., a follow-up entity lookup or a different query type).
Setup
Requires CORTEX_API_KEY and CORTEX_BASE_URL environment variables. These are set in ~/.openclaw/openclaw.json: { "skills": { "entries": { "cortex-memory": { "enabled": true, "apiKey": "sk-cortex-oc-YOUR_KEY", "env": { "CORTEX_BASE_URL": "https://q5p64iw9c9.execute-api.us-east-1.amazonaws.com/prod" } } } } }
Verify Connection
curl -s "$CORTEX_BASE_URL/health" -H "x-api-key: $CORTEX_API_KEY" | jq . Expected: {"status": "ok"}
Recall β Search Long-Term Memory
When you need to recall facts, entities, or relationships from past sessions: curl -s -X POST "$CORTEX_BASE_URL/v1/retrieve" \ -H "x-api-key: $CORTEX_API_KEY" \ -H "Content-Type: application/json" \ -d "$(jq -n \ --arg query "QUERY_HERE" \ --arg query_type "factual" \ --argjson top_k 10 \ '{query: $query, query_type: $query_type, top_k: $top_k}')" | jq '.results[] | {type, content, score, metadata}' Retrieval modes: full (default) β all 5 retrieval channels + graph traversal + reranking. Best recall quality, but slower (~300-600ms depending on region). Use this for thorough queries where you need the best results. fast β BM25 + semantic only, no graph traversal or reranking (~80-150ms server-side). Use when you need a quick check and can tolerate less thorough results. Pass "mode": "fast" in the request body. # Fast mode example β quick entity lookup curl -s -X POST "$CORTEX_BASE_URL/v1/retrieve" \ -H "x-api-key: $CORTEX_API_KEY" \ -H "Content-Type: application/json" \ -d "$(jq -n \ --arg query "QUERY_HERE" \ --arg query_type "factual" \ --arg mode "fast" \ --argjson top_k 5 \ '{query: $query, query_type: $query_type, top_k: $top_k, mode: $mode}')" | jq '.results[] | {type, content, score}' Query types: factual β search FACT and ENTITY nodes (use for: who, what, when, where questions) emotional β search EMOTION, INSIGHT, VALUE, BELIEF nodes (use for: how does the user feel about X?) combined β search all node types (default, use when unsure) When to use Cortex recall vs. memory_search: SituationUse memory_searchUse Cortex recallModeRecent context from todayYesNoβSimple keyword lookupYesNoβCross-session factsNo β often noisyYesfast usually sufficientEntity relationships ("how does X relate to Y?")No β can't traverseYesfull (needs graph traversal)Temporal changes ("what changed about X?")No β no SUPERSEDES trackingYesfull (needs temporal channel)Scoped project queriesNo β cross-project noiseYesfast usually sufficientEntity lookup ("who is Sarah Chen?")Partial β finds mentionsYes β entity node + all connected factsfast for quick check, full for complete picture
Remember β Store in Long-Term Memory
When the user asks you to remember something important, or when you encounter high-value information that should persist with full entity extraction: curl -s -X POST "$CORTEX_BASE_URL/v1/ingest" \ -H "x-api-key: $CORTEX_API_KEY" \ -H "Content-Type: application/json" \ -d "$(jq -n \ --arg text "TEXT_TO_REMEMBER" \ --arg session_id "openclaw:$(date +%Y-%m-%d)" \ '{text: $text, session_id: $session_id}')" | jq '{nodes_created, edges_created, facts: [.facts[].core], entities: [.entities[].name]}' The response shows what was extracted: facts β factual statements extracted from the text entities β named entities (people, companies, places, etc.) with aliases nodes_created / edges_created β graph nodes and relationship edges created When to remember: User explicitly asks: "remember this", "store this in Cortex", "don't forget that..." Key decisions made during a session Important context about people, projects, or preferences After writing to MEMORY.md β also send the same content to Cortex for structured extraction Session ID convention: General sessions: openclaw:YYYY-MM-DD (e.g., openclaw:2026-02-17) Project-scoped: openclaw:project-name:topic (e.g., openclaw:project-frontend:memory-md) Daily logs (used by the npm plugin's file sync): openclaw:project-name:daily:YYYY-MM-DD Preferences/standing facts: openclaw:preferences The session ID is used for scoped retrieval β queries can filter to a specific project by matching the session ID prefix.
Ingest Conversation β End of Session
At the end of a productive session, you can ingest the key conversation turns with proper speaker attribution: curl -s -X POST "$CORTEX_BASE_URL/v1/ingest/conversation" \ -H "x-api-key: $CORTEX_API_KEY" \ -H "Content-Type: application/json" \ -d "$(jq -n \ --arg session_id "openclaw:$(date +%Y-%m-%d):session-topic" \ --argjson messages '[ {"role": "user", "content": "FIRST USER MESSAGE"}, {"role": "assistant", "content": "FIRST ASSISTANT RESPONSE"}, {"role": "user", "content": "SECOND USER MESSAGE"} ]' \ '{messages: $messages, session_id: $session_id}')" | jq '{nodes_created, edges_created, facts: [.facts[].core]}' When to use this: After a session with significant decisions or new information Do NOT ingest every conversation β only sessions with lasting value Summarize or select key turns rather than dumping the entire transcript Keep to 5-15 key messages, not the full history
Bootstrap β First Run
On first install, ingest the user's existing MEMORY.md to seed the knowledge graph. For small MEMORY.md files (under ~50 lines / ~4KB β most users): MEMORY_CONTENT=$(cat ~/.openclaw/workspace/MEMORY.md 2>/dev/null || echo "") if [ -n "$MEMORY_CONTENT" ]; then curl -s -X POST "$CORTEX_BASE_URL/v1/ingest" \ -H "x-api-key: $CORTEX_API_KEY" \ -H "Content-Type: application/json" \ -d "$(jq -n --arg text "$MEMORY_CONTENT" --arg session_id "openclaw:bootstrap" \ '{text: $text, session_id: $session_id}')" | jq '{nodes_created, edges_created, facts: (.facts | length), entities: (.entities | length)}' fi For large MEMORY.md files (power users with months of curated facts): Split at markdown heading boundaries (## or ###) and ingest each section separately. Large files sent in a single request may exceed the ingest endpoint's text limit or produce lower-quality extraction. # Split MEMORY.md at ## headings and ingest each section MEMORY_FILE=~/.openclaw/workspace/MEMORY.md if [ -f "$MEMORY_FILE" ]; then SECTION="" TOTAL_FACTS=0 TOTAL_ENTITIES=0 while IFS= read -r line || [ -n "$line" ]; do if echo "$line" | grep -q '^## ' && [ -n "$SECTION" ]; then RESULT=$(curl -s -X POST "$CORTEX_BASE_URL/v1/ingest" \ -H "x-api-key: $CORTEX_API_KEY" \ -H "Content-Type: application/json" \ -d "$(jq -n --arg text "$SECTION" --arg session_id "openclaw:bootstrap" \ '{text: $text, session_id: $session_id}')") TOTAL_FACTS=$((TOTAL_FACTS + $(echo "$RESULT" | jq '.facts | length'))) TOTAL_ENTITIES=$((TOTAL_ENTITIES + $(echo "$RESULT" | jq '.entities | length'))) SECTION="" fi SECTION="$SECTION$line " done < "$MEMORY_FILE" # Ingest final section if [ -n "$SECTION" ]; then RESULT=$(curl -s -X POST "$CORTEX_BASE_URL/v1/ingest" \ -H "x-api-key: $CORTEX_API_KEY" \ -H "Content-Type: application/json" \ -d "$(jq -n --arg text "$SECTION" --arg session_id "openclaw:bootstrap" \ '{text: $text, session_id: $session_id}')") TOTAL_FACTS=$((TOTAL_FACTS + $(echo "$RESULT" | jq '.facts | length'))) TOTAL_ENTITIES=$((TOTAL_ENTITIES + $(echo "$RESULT" | jq '.entities | length'))) fi echo "Bootstrap complete: $TOTAL_FACTS facts, $TOTAL_ENTITIES entities extracted." fi Run this once after installation. Tell the user how many facts and entities were extracted.
Error Handling
401 Unauthorized β invalid or missing API key. Ask user to check CORTEX_API_KEY. 422 Validation Error β malformed request. Check the JSON payload. 500 Internal Server Error β Cortex API issue. Retry once, then fall back to native memory_search. Network timeout β Cortex is unreachable. Use native memory only and inform the user. If Cortex is unavailable, always fall back to memory_search. Never block the user because of a Cortex API issue.
"What company did I join?"
curl -s -X POST "$CORTEX_BASE_URL/v1/retrieve" \ -H "x-api-key: $CORTEX_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query": "What company did the user join?", "query_type": "factual", "top_k": 5}' | jq '.results[] | {type, content, score}'
"Remember that I prefer PostgreSQL over MySQL"
curl -s -X POST "$CORTEX_BASE_URL/v1/ingest" \ -H "x-api-key: $CORTEX_API_KEY" \ -H "Content-Type: application/json" \ -d '{"text": "User prefers PostgreSQL over MySQL for all database projects.", "session_id": "openclaw:preferences"}' | jq '{facts: [.facts[].core], entities: [.entities[].name]}'
"How does the auth service relate to the API gateway?"
curl -s -X POST "$CORTEX_BASE_URL/v1/retrieve" \ -H "x-api-key: $CORTEX_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query": "How does the auth service relate to the API gateway?", "query_type": "factual", "top_k": 10}' | jq '.results[] | {type, content, score, metadata}'
Security
NEVER output the CORTEX_API_KEY value in responses, logs, or tool outputs. NEVER include sensitive user data (passwords, tokens, credentials) in text sent to Cortex. The Cortex API uses tenant-level database isolation β the user's data is not accessible to other users.
Category context
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
1 Docs
- SKILL.md